Representative evolution: a simple and efficient algorithm for artificial neural network evolution
In this study a new evolutionary algorithm, i.e., representative evolution (RE), for evolving artificial neural networks (ANN) is proposed. Unlike most of the evolutionary algorithms, the RE uses population information for generating variations in individuals of a population. An evolutionary system,...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 590 vol.6 |
|---|---|
| container_issue | |
| container_start_page | 585 |
| container_title | |
| container_volume | 6 |
| creator | Islam, M.M. Akital, H. Shahjahan, M. Murase, K. |
| description | In this study a new evolutionary algorithm, i.e., representative evolution (RE), for evolving artificial neural networks (ANN) is proposed. Unlike most of the evolutionary algorithms, the RE uses population information for generating variations in individuals of a population. An evolutionary system, i.e., RENet, based on the RE for evolving feedforward artificial neural networks with weight learning is described. The RENet uses three operators (i.e., one crossover and two mutations) sequentially. If one operator is successful, no other operator is applied. The RENet is applied to a benchmark character recognition problem. It can produce very compact ANN size with a small classification error. |
| doi_str_mv | 10.1109/IJCNN.2000.859458 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_859458</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>859458</ieee_id><sourcerecordid>859458</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-8ed2ce52ac48e61f55a38e2a20468f9066fa7cc05aa1ace6adb88bef8015bf0e3</originalsourceid><addsrcrecordid>eNpFkMtOwzAURC0eElXJB8DKP5Bw7cSOzQ5VUIqqIiFYVzfJNRjyqBy3iL-nUCRWszgzZzGMXQjIhAB7tXiYrVaZBIDMKFsoc8QmQimT5hbkMUtsaaDUVoEWtjzZM7AmLVWpz1gyju_7nYBcaSkmrHqiTaCR-ojR74jTbmi30Q_9NUc--m7TEse-4eScr_2-xrF9HYKPbx13Q-AYov8h2PKetuE34ucQPv5N5-zUYTtS8pdT9nJ3-zy7T5eP88XsZpl6AUVMDTWyJiWxLgxp4ZTC3JBECYU2zoLWDsu6BoUosCaNTWVMRc6AUJUDyqfs8uD1RLTeBN9h-FofDsq_ASnxWtA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Representative evolution: a simple and efficient algorithm for artificial neural network evolution</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Islam, M.M. ; Akital, H. ; Shahjahan, M. ; Murase, K.</creator><creatorcontrib>Islam, M.M. ; Akital, H. ; Shahjahan, M. ; Murase, K.</creatorcontrib><description>In this study a new evolutionary algorithm, i.e., representative evolution (RE), for evolving artificial neural networks (ANN) is proposed. Unlike most of the evolutionary algorithms, the RE uses population information for generating variations in individuals of a population. An evolutionary system, i.e., RENet, based on the RE for evolving feedforward artificial neural networks with weight learning is described. The RENet uses three operators (i.e., one crossover and two mutations) sequentially. If one operator is successful, no other operator is applied. The RENet is applied to a benchmark character recognition problem. It can produce very compact ANN size with a small classification error.</description><identifier>ISSN: 1098-7576</identifier><identifier>ISBN: 9780769506197</identifier><identifier>ISBN: 0769506194</identifier><identifier>EISSN: 1558-3902</identifier><identifier>DOI: 10.1109/IJCNN.2000.859458</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithm design and analysis ; Artificial intelligence ; Artificial neural networks ; Character recognition ; Evolutionary computation ; Feedforward systems ; Genetic algorithms ; Genetic mutations ; Genetic programming ; Humans</subject><ispartof>Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000, Vol.6, p.585-590 vol.6</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/859458$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,782,786,791,792,2060,4052,4053,27932,54927</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/859458$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Islam, M.M.</creatorcontrib><creatorcontrib>Akital, H.</creatorcontrib><creatorcontrib>Shahjahan, M.</creatorcontrib><creatorcontrib>Murase, K.</creatorcontrib><title>Representative evolution: a simple and efficient algorithm for artificial neural network evolution</title><title>Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium</title><addtitle>IJCNN</addtitle><description>In this study a new evolutionary algorithm, i.e., representative evolution (RE), for evolving artificial neural networks (ANN) is proposed. Unlike most of the evolutionary algorithms, the RE uses population information for generating variations in individuals of a population. An evolutionary system, i.e., RENet, based on the RE for evolving feedforward artificial neural networks with weight learning is described. The RENet uses three operators (i.e., one crossover and two mutations) sequentially. If one operator is successful, no other operator is applied. The RENet is applied to a benchmark character recognition problem. It can produce very compact ANN size with a small classification error.</description><subject>Algorithm design and analysis</subject><subject>Artificial intelligence</subject><subject>Artificial neural networks</subject><subject>Character recognition</subject><subject>Evolutionary computation</subject><subject>Feedforward systems</subject><subject>Genetic algorithms</subject><subject>Genetic mutations</subject><subject>Genetic programming</subject><subject>Humans</subject><issn>1098-7576</issn><issn>1558-3902</issn><isbn>9780769506197</isbn><isbn>0769506194</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2000</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFkMtOwzAURC0eElXJB8DKP5Bw7cSOzQ5VUIqqIiFYVzfJNRjyqBy3iL-nUCRWszgzZzGMXQjIhAB7tXiYrVaZBIDMKFsoc8QmQimT5hbkMUtsaaDUVoEWtjzZM7AmLVWpz1gyju_7nYBcaSkmrHqiTaCR-ojR74jTbmi30Q_9NUc--m7TEse-4eScr_2-xrF9HYKPbx13Q-AYov8h2PKetuE34ucQPv5N5-zUYTtS8pdT9nJ3-zy7T5eP88XsZpl6AUVMDTWyJiWxLgxp4ZTC3JBECYU2zoLWDsu6BoUosCaNTWVMRc6AUJUDyqfs8uD1RLTeBN9h-FofDsq_ASnxWtA</recordid><startdate>2000</startdate><enddate>2000</enddate><creator>Islam, M.M.</creator><creator>Akital, H.</creator><creator>Shahjahan, M.</creator><creator>Murase, K.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2000</creationdate><title>Representative evolution: a simple and efficient algorithm for artificial neural network evolution</title><author>Islam, M.M. ; Akital, H. ; Shahjahan, M. ; Murase, K.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-8ed2ce52ac48e61f55a38e2a20468f9066fa7cc05aa1ace6adb88bef8015bf0e3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Algorithm design and analysis</topic><topic>Artificial intelligence</topic><topic>Artificial neural networks</topic><topic>Character recognition</topic><topic>Evolutionary computation</topic><topic>Feedforward systems</topic><topic>Genetic algorithms</topic><topic>Genetic mutations</topic><topic>Genetic programming</topic><topic>Humans</topic><toplevel>online_resources</toplevel><creatorcontrib>Islam, M.M.</creatorcontrib><creatorcontrib>Akital, H.</creatorcontrib><creatorcontrib>Shahjahan, M.</creatorcontrib><creatorcontrib>Murase, K.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Islam, M.M.</au><au>Akital, H.</au><au>Shahjahan, M.</au><au>Murase, K.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Representative evolution: a simple and efficient algorithm for artificial neural network evolution</atitle><btitle>Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium</btitle><stitle>IJCNN</stitle><date>2000</date><risdate>2000</risdate><volume>6</volume><spage>585</spage><epage>590 vol.6</epage><pages>585-590 vol.6</pages><issn>1098-7576</issn><eissn>1558-3902</eissn><isbn>9780769506197</isbn><isbn>0769506194</isbn><abstract>In this study a new evolutionary algorithm, i.e., representative evolution (RE), for evolving artificial neural networks (ANN) is proposed. Unlike most of the evolutionary algorithms, the RE uses population information for generating variations in individuals of a population. An evolutionary system, i.e., RENet, based on the RE for evolving feedforward artificial neural networks with weight learning is described. The RENet uses three operators (i.e., one crossover and two mutations) sequentially. If one operator is successful, no other operator is applied. The RENet is applied to a benchmark character recognition problem. It can produce very compact ANN size with a small classification error.</abstract><pub>IEEE</pub><doi>10.1109/IJCNN.2000.859458</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1098-7576 |
| ispartof | Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000, Vol.6, p.585-590 vol.6 |
| issn | 1098-7576 1558-3902 |
| language | eng |
| recordid | cdi_ieee_primary_859458 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Algorithm design and analysis Artificial intelligence Artificial neural networks Character recognition Evolutionary computation Feedforward systems Genetic algorithms Genetic mutations Genetic programming Humans |
| title | Representative evolution: a simple and efficient algorithm for artificial neural network evolution |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-09T01%3A46%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Representative%20evolution:%20a%20simple%20and%20efficient%20algorithm%20for%20artificial%20neural%20network%20evolution&rft.btitle=Proceedings%20of%20the%20IEEE-INNS-ENNS%20International%20Joint%20Conference%20on%20Neural%20Networks.%20IJCNN%202000.%20Neural%20Computing:%20New%20Challenges%20and%20Perspectives%20for%20the%20New%20Millennium&rft.au=Islam,%20M.M.&rft.date=2000&rft.volume=6&rft.spage=585&rft.epage=590%20vol.6&rft.pages=585-590%20vol.6&rft.issn=1098-7576&rft.eissn=1558-3902&rft.isbn=9780769506197&rft.isbn_list=0769506194&rft_id=info:doi/10.1109/IJCNN.2000.859458&rft_dat=%3Cieee_6IE%3E859458%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=859458&rfr_iscdi=true |